Copertina

Demystifying OPD: Length Inflation and Stabilization Strategies for Large Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Luo, Feng, Chuang, Yu-Neng, Wang, Guanchu, Xu, Zicheng, Han, Xiaotian, Zhang, Tianyi, Braverman, Vladimir
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Self-ensemble: Mitigating Confidence Mis-calibration for Large Language Models
di: Xu, Zicheng, et al.
Pubblicazione: (2025)

DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching
di: Xu, Zicheng, et al.
Pubblicazione: (2025)

AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Models
di: Luo, Feng, et al.
Pubblicazione: (2025)

FaithLM: Towards Faithful Explanations for Large Language Models
di: Chuang, Yu-Neng, et al.
Pubblicazione: (2024)

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization
di: Chuang, Yu-Neng, et al.
Pubblicazione: (2025)

Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansion
di: Wang, Guanchu, et al.
Pubblicazione: (2024)

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
di: Sui, Yang, et al.
Pubblicazione: (2025)

Demystifying Verbatim Memorization in Large Language Models
di: Huang, Jing, et al.
Pubblicazione: (2024)

DP-OPD: Differentially Private On-Policy Distillation for Language Models
di: Khadem, Fatemeh, et al.
Pubblicazione: (2026)

Random Text, Zipf's Law, Critical Length,and Implications for Large Language Models
di: Berman, Vladimir
Pubblicazione: (2025)

Demystifying Embedding Spaces using Large Language Models
di: Tennenholtz, Guy, et al.
Pubblicazione: (2023)

Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?
di: Wang, Shouren, et al.
Pubblicazione: (2025)

Tackling Length Inflation Without Trade-offs: Group Relative Reward Rescaling for Reinforcement Learning
di: Li, Zichao, et al.
Pubblicazione: (2026)

Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language Models
di: Li, Zhaoyi, et al.
Pubblicazione: (2026)

Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models
di: Chen, Pin-Yu, et al.
Pubblicazione: (2025)

CodeJudge: Evaluating Code Generation with Large Language Models
di: Tong, Weixi, et al.
Pubblicazione: (2024)

OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification
di: Zhou, Yuhang, et al.
Pubblicazione: (2026)

LAS: Loss-less ANN-SNN Conversion for Fully Spike-Driven Large Language Models
di: Chen, Long, et al.
Pubblicazione: (2025)

SELF: Self-Extend the Context Length With Logistic Growth Function
di: Dang, Phat Thanh, et al.
Pubblicazione: (2025)

Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding
di: Yi, Hanling, et al.
Pubblicazione: (2024)

Demystifying and Enhancing the Efficiency of Large Language Model Based Search Agents
di: Yang, Tiannuo, et al.
Pubblicazione: (2025)

BiTA: Bi-Directional Tuning for Lossless Acceleration in Large Language Models
di: Lin, Feng, et al.
Pubblicazione: (2024)

Demystifying Language Model Forgetting with Low-rank Example Associations
di: Jin, Xisen, et al.
Pubblicazione: (2024)

Demystifying Low-Rank Knowledge Distillation in Large Language Models: Convergence, Generalization, and Information-Theoretic Guarantees
di: Soarez, Alberlucia Rafael, et al.
Pubblicazione: (2026)

Hansel: Output Length Controlling Framework for Large Language Models
di: Song, Seoha, et al.
Pubblicazione: (2024)

The Role of Deductive and Inductive Reasoning in Large Language Models
di: Cai, Chengkun, et al.
Pubblicazione: (2024)

FairPy: A Toolkit for Evaluation of Prediction Biases and their Mitigation in Large Language Models
di: Viswanath, Hrishikesh, et al.
Pubblicazione: (2023)

MAD-OPD: Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate
di: Wang, Jianze, et al.
Pubblicazione: (2026)

Intrinsic Entropy of Context Length Scaling in LLMs
di: Shi, Jingzhe, et al.
Pubblicazione: (2025)

Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining
di: Zhang, Haochen, et al.
Pubblicazione: (2025)

Draft-OPD: On-Policy Distillation for Speculative Draft Models
di: Lei, Haodi, et al.
Pubblicazione: (2026)

Learning to Compress Prompt in Natural Language Formats
di: Chuang, Yu-Neng, et al.
Pubblicazione: (2024)

Demystifying Singular Defects in Large Language Models
di: Wang, Haoqi, et al.
Pubblicazione: (2025)

Fast and Effective Weight Update for Pruned Large Language Models
di: Boža, Vladimír
Pubblicazione: (2024)

Stabilizing Efficient Reasoning with Step-Level Advantage Selection
di: Wang, Han, et al.
Pubblicazione: (2026)

SmartThinker: Progressive Chain-of-Thought Length Calibration for Efficient Large Language Model Reasoning
di: Hu, Chenzhi, et al.
Pubblicazione: (2026)

Assessing and Enhancing Large Language Models in Rare Disease Question-answering
di: Wang, Guanchu, et al.
Pubblicazione: (2024)

Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model
di: Liu, Zirui, et al.
Pubblicazione: (2023)

Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation
di: Zhang, Hongxiang, et al.
Pubblicazione: (2025)

Automated Alignment of Math Items to Content Standards in Large-Scale Assessments Using Language Models
di: Xu, Qingshu, et al.
Pubblicazione: (2025)